Cursor 설치 가이드
개발자용 MCP 서버와 함께 자주 쓰이는 AI 코드 에디터.
MCP Servers
This MCP server enables dynamic creation, editing and saving of PowerPoint presentations. Built upon the MCP and using the python-pptx library, it provides a flexible interface to add slides, images,...
This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).
kali linux mcp,pentest,penetration test
built by an autonomous agent · sibyl labs llc
Enhanced note taking for AI Agents with supervision.
Turn any OpenAPI spec into a native CLI binary. No MCP, no bloat, no runtime dependencies, ONLY CLI.
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency
- Let AI assistants analyze binaries directly
Fictional concept interface—not an actual Codex UI or a measured context, token, speed, or latency benchmark.
Persistent memory system for agentic AI via MCP - remember, recall, forget with semantic search with knowledge graph
Perplexity Advanced MCP is an advanced integration package that leverages the OpenRouter and Perplexity APIs to provide enhanced query processing capabilities.
A CLI tool for managing MCP servers configurations for MCP clients.
Agent Skills
一个专注毕业论文生产的 Claude Code skill，针对中文理工科毕业论文的写作风格调整和内容审校。目标是让论文读起来是有脑子的活人研究生写的。
This repo answers how well can agents use Supabase across various tasks.
OpenClaw skill and helper CLI for generating or editing images through the ChatGPT/Codex backend with local OAuth credentials.
A provider-aware plugin for auto-maintained LLM wikis — based on Andrej Karpathy's LLM Wiki pattern.
Everything else you see here is just the source code behind that file — you don't need to touch it.
We use Kimi-K2.5 as the MLLM and Z-Image-Turbo / Qwen-Image-2512 as the Generator. We use Sglang to serve MLLM and Diffusers to serve the Generator.
輸入股票代碼，自動從 Goodinfo.tw 讀取公開財報數據，生成互動式三維財務分析儀表板。
PRFlow is the Claude Code plugin that closes that gap — it carries one feature request all the way to a , so you do the final review and merge, not the cleanup.
A pre-built configuration that gives Claude Code persistent memory, security guardrails, and structured workflows. Clone, run setup.sh, and your next session picks up where the last one left off.
Every agentic runtime does the same thing: read a skill, call an LLM, execute tools, loop. SubZeroClaw is that principle written directly in C — no framework, no abstractions, no architecture...
Offense, defense, and the reverse-engineering and code-audit core both sides share. Every skill is fact-checked against primary sources.
Automatically updates your terminal window title to reflect the current task Claude Code is working on. Perfect for developers managing multiple Claude Code instances across different terminals.